研究生: |
陳世龍 SHIH - LONG CHEN |
---|---|
論文名稱: |
整合影像檢索與小波轉換之畫風合成系統 A Wavelet Sub-band Based Painting Style Synthesis Method Embedded in a Image Retrieval System |
指導教授: |
陳建中
Jiann-Jone Chen |
口試委員: |
張意政
none 唐政元 none 蔡超人 Chau-Ren Tsai 郭景明 Jing-ming Guo |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2008 |
畢業學年度: | 96 |
語文別: | 中文 |
論文頁數: | 63 |
中文關鍵詞: | 畫風合成 、影像檢索 、小波轉換 、正規化相關係 |
外文關鍵詞: | Painting Style Synthesis, Image Retrieval, Wavelet Transform, Normal Correlation Coefficient |
相關次數: | 點閱:194 下載:4 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
材質合成(Texture Synthesis)在電腦圖學(Computer Graphic)中的應用非常的廣泛,舉凡數位影像的編輯(Digital Image editing)或是立體影像的模擬,或是畫風的合成及轉換,都是靠材質合成來完成。畫風合成乃是參考藝術家的畫作,擷取畫作中的色彩及紋理,將其融合到輸入的照片中,產生兼具輸入照片的輪廓及藝術家畫作的色彩及紋理的影像,但要合成一張畫作,往往需要耗費電腦大量的運算來尋找最適合成區塊,而且若使用不適當藝術畫作來做為合成的參考依據,終究無法輸出令人滿意的結果。本論文提出一個完整的系統化架構其包含檢索系統和合成系統。檢索系統能夠依照使用者所指定的檢索特徵,去檢索出適合轉換的藝術家畫作,而合成系統則利用小波轉換對檢索得到的藝術家畫作及使用者輸入的影像中快速的影像進行合成。本篇論文最主要的貢獻在於建構一個完整的系統化架構,依據使用者所輸入的影像及所指定的檢索特徵,至藝術家資料庫中檢索出最適當的藝術家畫作,並利用小波轉換來進行畫風合成,有效減少畫風合成的時間。
Texture synthesis has been widely applied in computer vision, e.g., the results of digital image editing and 3D computer graphic are produced by texture synthesis. Painting synthesis extracts the color and texture from artistic paintings and synthesizes with the picture of user input. The synthesized image preserves not only color and texture of an artistic painting but also the adumbration of a user input picture. Searching the best matched block during the synthesizing process is time consuming and the synthesized result may likely to be unsatisfied resulted from synthesized with improper artistic paintings. To solve this problem, we proposed to integrate this synthesis procedure with an image retrieval engine to eliminate improper computations. Given one input image, the retrieval system would tentatively find out some candidate painting images, from which the user would select for synthesizing with the input image. In addition, we proposed to perform wavelet decomposition to reduce the time complexity and to eliminate the block artifact due to block-based matching process in synthesis. Experiments show that synthesized images demonstrate better subjective performance and requiring shorter execution time, as compared to previous researches.
[1] M. Ashikahmin, J. F. Hughes and C.H. Sequin, “Synthesizing natural textures,” proc. 2001 Synp. Interactive 3D Graphics, pp. 217-226, 2001.
[2] A. Efros and W. T. Freeman, “Image quilting for texture synthesis and transfer,” Proc. SIGGRAPH 2001, pp. 341-346, 2001.
[3] A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salesin, “Image Analogies,” in Proc. SIGGRAPH 2001, pp. 327-340, 2001.
[4] L. Liang, C. Liu, Y. Q. Xu, B. Guo, and H. Y. Shum, “Real-time texture synthesis by patch-based sampling,” ACM Trans. Graphics, pp. 127-150, 2001.
[5] L. Y. Wei, “Deterministic texture analysis and synthesis using tree structure vector quantization,” in Proceedings of XII Brazilian Symposium on Computer Graphics and Image (SIBGRAPI 1999), pp. 207-213, October 1999.
[6] L. Y. Wei and M. Levoy, “Fast texture synthesis using tree-structured vector Quantization,” Proc. SIGGRAPH 2000, pp. 479-488, 2000.
[7] C. Y. Liu, J. J. Chen and F. C. Chang, “A dynamically adapted retrieval algorithm for multi-instances image query with heterogeneous features,” IEEE Consumer Communication and Networking Conference, 2004.
[8] H. G. Stark , “Wavelets and signal processing,” Springer, 2005.
[9] A. Efros and T. Leung, “Texture synthesis by non-parametric sampling,” in Proc. IEEE Int. Conf. Computer Vision (ICCV ’99), pp. 1033-1038, 1999.
[10] C. Sidney Burrus, Ramesh A. Copmath, and Haitao Guo, “Introduction to wavelets and Wavelet Transform,” Prentice-Hill, 1998.
[11] M. Haindl, V. Havlicek, “A simple multispectral multi-resolution Markov texture model,” in Proceedings International Workshop on Texture Analysis and Synthesis, pp. 63-66, 2002.
[12] K. Popat and R. W. Picard, “Novel cluster-based probability model for texture synthesis, classification, and compression,”in Proc. SPIE Visual Communications and Image Processing, pp. 756-768,1993.
[13] J. S. D. Bonet , “Multiresolution sampling procedure for analysis and synthesis of texture images,” in Proceedings of SIGGRAPH 1997, pp. 361-368, August 1997.
[14] L. Y. Wei, “Texture synthesis by fixed neighborhood searching,” Ph.D. Thesis, Department of Computer Science, Stanford University, USA, Nov. 2001.
[15] L. Y. Wei, M. Levoy, “Order-independent texture synthesis,” Technical Report TR-2002-01, Department of Computer Science, Stanford University, 2002.
[16] Y. Q. Xu, B. Guo, and H. Y. Shum, “Chaos mosaic: fast and memory efficient texture synthesis,” Microsoft Research Technical Reports, 94 MsR-TR-2000-32, April 2000.
[17] G. R. Cross and A. K. Jain. “Markov random field texture models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 25–39, January 1983.
[18] R. Szeliski, and H. Y. Shum, “Creating full view panoramic mosaics and environment maps,” in Proceedings of SIGGRAPH 1997, pp. 251-258, August 1997.
[19] E. Kasutani, A. Yamada, “The MPEG-7 color layout descriptor: A compact image feature description for high-speed image/video segment retrieval,” IEEE Proc. of International Conference on Image Processing (ICIP 2001), vol. I, pp. 674-677, October 2001.
[20] C. S. Won, D. K. Park, and S. J. Park, “Efficient use of MPEG-7 edge histogram descriptor,” ETRI Journal, vol. 24, no. 1, pp. 23-30, Feb. 2002.
[21] M. Bertalmin, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” in Proc. ACM conf. Computer Graphics, pp. 417-424, Jul. 2000.
[22] D. J. Heeger and J. R. Bergen, “Pyramid-based texture analysis/synthesis,” in Proceedings of SIGGRAPH 1995, pp. 229-238, 1995.
[23] J. J. Chen, C. J. Hu and C. R. Su, “Scalable retrieval and mining with optimal peer-to-peer configuration,” IEEE Transactions on Multimedia, vol. 10, Feb 2008.
[24] Artists category, http://www.allposters.com/